Face mask detection in foggy weather from digital images using transfer learning

ABSTRACT

Community mask use is an efficacious non-pharmacologic way to minimize viral infection spread. It is a recommendation that individuals wear face masks as protective gear. Under ideal weather conditions, machine and artificial intelligence techniques can typically determine if a person is wearing a mask properly. Identification becomes more difficult under inclement weather such as fog, clouds, haze or rain. In this work, we propose a technique that can detect a human face wearing a mask even in adverse weather. For this, homogeneous foggy images have been considered. The main challenge with this problem is that video quality degrades because of fog. Here, diverse Deep learning models train regular datasets containing digital pictures of persons with facial and non-facial masks. The training and validation parameters ensure 97% accuracy in classifying faces wearing a mask.

KEYWORDS:

• Deep learning
• fog
• haze
• facemask
• transfer learning
• CNN
• defogging
• MobileNet‌

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Isha Kansal

Dr. Isha Kansal is currently working as Assistant Professor in Chitkara University Institute of Engineering and Technology, CU Punjab. Dr. Isha has attained her doctorate degree from Thapar Institute of Engineering and Technology, Punjab. Her both M.Tech (CSE) (from Thapar Institute of Engineering and Technology) and B.Tech (CSE) (from BBSBEC Fatehgarh Sahib) degrees are with distinction. She has about 7 SCI Publications and number of publications in renowned International Journals and fully refereed International Conferences with the experience of more than 9 years. Recently, she has been Certified under Wipro Talent Next Program in JAVA. Her main areas of research are Image /Video processing, Machine and Deep Learning.

Vikas Khullar

Dr Vikas Khullar is currently working as an Associate Professor at Department of Computer Science and Engineering, Chitkara University Institute of Engineering and Technology, Chitkara University, Patiala, Punjab, India. He has 15 years of experience in research and academia.

Dr Khullar has completed his Ph.D. in Computer Science and Engineering. During his Doctorate dissertation, he had developed new and unique assistive technologies with the use of machine learning and deep learning along with IOT and embedded hardware.

He has published more than 70 publications. His major findings are published in reputed/indexed journals with significant impact factors. He has filed 30 patents to tackle most social and commercial problems. He has acted as a team leader and has organized a number of international/national conferences, short term courses, faculty development programmes, seminars and webinars. At present, he is working in the field of Intelligent Internet of Things in Society 5.0, Assistive Technologies for Neurological Disorders, Federated Learning and Trusted Artificial Intelligence.

Renu Popli

Dr Renu Popli is currently working as an Assistant Professor at Department of Computer Science and Engineering, Chitkara University Institute of Engineering and Technology, Chitkara University, Patiala, Punjab, India. He has 9 years of experience in research and academia. She received her M.Tech and Ph.D Degrees in Computer Science from Kurukshetra University, Kurukshetra, India in 2012 and 2018, respectively. She has published more than 30 publications in renowned International Journals and fully refereed International Conferences. She has filed more than 10 patents in multiple domains. Her research interest includes Mobile ad-hoc, wireless sensor networks, ML, DL and IoT.

Jyoti Verma

Jyoti Verma is pursuing her Ph.D. in Computer Engineering from Punjabi University, Patiala, India, and holds an M. Tech degree in Computer Science and Engineering from Dr. B.R Ambedkar NIT, Jalandhar, India. She obtained her bachelor's degree (B. Tech) in Computer Engineering from Kurukshetra University, India, in 2002. Jyoti has more than 15 years of experience in teaching. She worked as Assistant Professor at Chitkara University, Punjab, India, and Lingaya's University, Haryana, India. Jyoti is pursuing her doctoral degree (Ph.D.) in Computer Engineering from Punjabi University, Patiala, India. Her research work has been widely recognized, and she has published several papers in top-tier peer-reviewed journals. Jyoti has also edited technical books and served as a reviewer for several journals. She holds several patents in cross-functional domains, demonstrating her ability to bring innovative ideas to fruition.

Rajeev Kumar

Dr. Rajeev Kumar received his BTech and MTech Degrees in Electronics and Communication Engineering from Kurukshetra University, Kurukshetra, India in 2008 and 2010, respectively. He completed his PhD degree in Electronics Engineering from Banasthali University, Rajasthan, India in 2017. He is currently working as an Assistant Professor in Department of Electronics and Communication Engineering, Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India. His research interests include reconfigurable antenna, ultra-wideband antenna, dual band/triple band microstrip antennas for wireless communication, smart and MIMO antennas systems and also include Internet of Things (IOT).